Scholar
Yixuan Ren
Google Scholar ID: TFpdak8AAAAJ
University of Maryland - College Park
Citations & Impact
Citations
486
H-index
5
i10-index
5
Publications
7
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - NeRV-Diffusion: Diffuse Implicit Neural Representation for Video Synthesis (Under Review, 2024)
- - Video Diffusion Models Encode Motion in Early Timesteps (Under Review, 2024)
- - LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR, 2025 Oral)
- - Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models (ECCV, 2024)
- - Content-Adaptive Image Color Editing with Auxiliary Color Restoration Tasks (WACV, 2024)
- - Towards Scalable Neural Representation for Diverse Videos (CVPR, 2023)
- - NeRV: Neural Representations for Videos (NeurIPS, 2021)
- - StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis (CVPR, 2021)
Research Experience
- - Research Scientist Intern, Meta GenAI, 2025, Mentors: Mannat Singh, Saketh Rambhatla, Andrew Brown, Arun Mallya
- - Research Scientist Intern, Adobe Research, 2023, Mentors: Yang Zhou, Jimei Yang, Jing Shi, Difan Liu, Feng Liu
- - Research Scientist Intern, Adobe Research, 2022, Mentors: Jing Shi, Zhifei Zhang, Yifei Fan, Zhe Lin
- - Research Intern, ByteDance, 2021, Mentors: Xiao Yang, Bingchen Liu, Yizhe Zhu
Education
- - Ph.D.: Department of Computer Science, University of Maryland, College Park, Advisor: Prof. Abhinav Shrivastava, Expected Graduation: 2026
- - M.S.: University of Maryland, College Park
- - B.E.: Tsinghua University
Background
- - Research Interests: Image and video synthesis and editing, generative models, and visual tokenizers
- - Field: Computer Science
- - Brief Introduction: A final-year Ph.D. student in the Department of Computer Science at the University of Maryland, College Park, focusing on image and video generation models, visual tokenizers, and video implicit neural representations.
Miscellany
- - Personal Interests: Seeking full-time research opportunities, particularly in image/video generative modeling
Co-authors